Socure, Inc.

Berbix LLC

Eric Levine

Stephen Kirkham

Pablo Ysrrael Abreu

Edward Li

Badri Nagabandi

Hayden Edelson

Feng Xiao

Methods, systems, and devices are provided for an authentication system configured to verify the identity of a person. According to one aspect, the system can determine that a first set of image pixels contains a first side of an authentication document. The system can determine that a second set of image pixels contains a second side of an authentication document. The system can determine whether the first side of the authentication document of the first image and the second side of the authentication document match. The system can compare a third image with the first image and determine whether the third image and the first image match to the same person. And the system can perform each step of authentication after receiving an image and prior to requesting more images from the user, reducing the overall processing time.

Identity authentication and processing

Provided is a system and methodology which enhances the readability of barcodes using machine learning techniques wherein a model is trained using exemplary data and the resulting model is used in production to increase the chances of successfully capturing the data in a barcode notwithstanding that the barcode may be of low quality. According to the teachings of the present invention, the system is trained using large quantities of synthetic personal information associated with barcodes. Once the system is placed into production, the trained model is applied as against newly identified barcodes to enhance the readability of the original barcode based on features associated with the trained model.

Generative system and method for enhancing readability of barcodes using frequency guided computer vision

Methods, systems, and devices are provided for authentication system configured to authenticate a document. According to one aspect, the system can receive image capture data including one or more virtual images of the document. The system can detect one or more identification indicators in the one or more virtual images. The system can detect one or more authentication indicators in the one or more virtual images. And the system can detect whether the document is authentic based on a result including analyzing the one or more identification indicators and analyzing the one or more authentication indicators.

Virtual authentication detection

Growing community of inventors

San Francisco, CA, United States of America

Eric Levine